Facebook Plunges Again
Tumblr 101: Tips And Tricks To Get Started
4-way HTML5 speed test: Firefox 3.7 faster than Internet Explorer 9 (video)
As you will see from the video, Chrome (even with hardware acceleration turned on via command line switches) is in a distant last place, miles behind both Firefox and IE. Opera competes well up to a point, but eventually gives way to Firefox and IE with 1000 fishies swimming about.
I state in the video that Opera is hardware accelerated, but I could be wrong (we've confirmed that they have hardware acceleration devs on staff, but don't know what's under Opera's hood just yet). Chrome also performs very poorly, even though it (apparently) has hardware acceleration. Incidentally, if you want to turn on hardware acceleration in Firefox 3.7, follow this guide.
Both Firefox and IE9 use Direct2D to utilize the GPU's rendering power -- so it's probably no surprise that they both show very similar results. It's most apparent when comparing CPU use; IE9 and FF3.7 are both miles ahead in performance, but both show the lowest CPU utilization!
Still, I'm certain Chrome will feature full hardware acceleration soon enough. The thing I'm most interested in is whether we'll see cross-platform hardware acceleration. Direct2D doesn't exist on either Mac or Linux -- so we'll see how it pans out! Meanwhile, if anyone wants to pit Opera or Chrome against Firefox on Linux, I'd be very interested to see the results.
Comments
49
Subscribe to commentsjackJun 25th 2010 11:53AM
This benchmark is flawed in Chrom. It says that I have 8 fps in it, but I SEE it is no more than 1fps (screen refresh approximetyly once a second). In opera 10.60 it says 10fps and it is quite smooth.
Mohamed MansourJun 29th 2010 7:10PM
For your information, Google Chrome (Chromium) does not have GPU renderering yet. These flags: --enable-gpu-rendering --enable-video-layering are not what you think they are. They are to enable experimental GPU rendering for backing store and video. The rendering you see currently is through Skia, not GPU. Someone is looking at it though, perhaps we should remove that flag, or just rename it.
Sebastian AnthonyJun 29th 2010 7:13PM
Ya, I think we sussed that out eventually :)
Thanks for the definitive info tho'!
eturkJul 31st 2010 4:27AM
IE9 creams Firefox 4b2. I've got an Asus with Core i7-Q720 & nVidia 360M
running each dish test at 1280x720
I have to get IE9 up to 500 fish before it drops from 60fps. @500 it does 32fps
Firefox 4 crawls at 3fps. No contest!
GPU-Z shows 15% load for IE9, only 5% for Firefox. Bravo MS!
BucksterMcgeeAug 25th 2010 10:54PM
Did you turn on GPU acceleration in FF4? It's not on by default.
Santosh PatilAug 30th 2010 11:19AM
Does IE9 beta support XP 64 bit ? Is the final version gonna support ?
BucksterMcgeeAug 25th 2010 11:06PM
So have you tried this with the most recent versions? I just did a few test on both the latest FF4 build and the IE9 preview 4, and IE9 seems to be out performing FF4 beta slightly about 3% (which isn't much).
I did a test like this with the Fish Tank, as well as the Psychedelic and Hallucinogenic tests.
Fish Tank: 944x925 (used Windows 7 aero snap to each side, but had to tweak IE9's height a bit so they were pixel for pixel the same size)
IE9: 500 fish 45fps, 1000 fish 26fps
FF4: 500 fish, 41fps, 1000 fish 21fps
For every amount of fish below 500 both ran at 60fps. Also, unlike this video I ran each test by themselves, and restarted each 4 times to check for variations.
For the Psychedelic and Hallucinogenic tests I ran each 4 times on both and recorded the values. The averages are shown as well.
IE9: psychedelic: 1850, 1810, 1845, 1827; average: 1833
IE9: hallucinogenic: 606, 616, 633, 603; average; 615
FF4: psychedelic: 1712, 1774, 1774, 1774; average: 1759,
FF4: hallucinogenic: 596, 599, 599, 599; average: 598.25
So these versions IE9 has the slight upper hand, we'll have to see what final versions are like.
(Interesting note: While IE9 seemed to go up and down more between test, FF4 seems to be pretty consistent, not sure what the difference is.)
Sebastian AnthonyAug 26th 2010 7:48AM
Good figures -- and good to see, even though I had all four open at the same time, that we got similar results :)
jeromeSep 10th 2010 2:26PM
This comparison is not usefull.
there is overlaps between the windows which cause some overhead in the display for the background application. (the system has to calculate the transparency)
Also Windows bring more power to the active application, the others works in background, reducing their priority.
You have to run only 1 browser at a time, in full screen mode for a more realistic comparison. and you have to compare more than 1 test page. each test page demonstrating different capabilities. so you could be good on 1 test and fail the second!
its a good try... but try again :)